Comments (4)
The original code for the paper used this fork & commit for Fairseq shamilcm/fairseq-py@ceb2f12. As written in the README there, it uses PyTorch 0.2 compiled from source. The whole setup is very outdated. You could alternatively use PyTorch 0.4.1 installed normally with Fairseq 0.5, if you use scripts from fairseq0.5
branch of this repo (https://github.com/nusnlp/mlconvgec2018/tree/fairseq0.5)
from mlconvgec2018.
Thanks a lot for your quick and kind reply. I just tried what you told me and the error didn't show up anymore!
But now another error came up.
When I ran below
./run.sh ./data/test/conll14st-test/conll14st-test.tok.src ./data/test/conll14st-test/output 0 ./training/models/mlconv/model1000
I got this error
++ source paths.sh
+++++ dirname paths.sh
++++ cd .
++++ pwd
+++ BASE_DIR=/mnt/data/okabe/mlconvgec2018
+++ DATA_DIR=/mnt/data/okabe/mlconvgec2018/data
+++ MODEL_DIR=/mnt/data/okabe/mlconvgec2018/models
+++ SCRIPTS_DIR=/mnt/data/okabe/mlconvgec2018/scripts
+++ SOFTWARE_DIR=/mnt/data/okabe/mlconvgec2018/software
++ '[' 4 -ge 4 ']'
++ input_file=./data/test/conll14st-test/conll14st-test.tok.src
++ output_dir=./data/test/conll14st-test/output
++ device=0
++ model_path=./training/models/mlconv/model1000
++ '[' 4 -eq 6 ']'
++ [[ -d ./training/models/mlconv/model1000 ]]
++ [[ -f ./training/models/mlconv/model1000 ]]
++ [[ ! -e ./training/models/mlconv/model1000 ]]
++ echo 'Model path not found: ./training/models/mlconv/model1000'
Model path not found: ./training/models/mlconv/model1000
++ FAIRSEQPY=/mnt/data/okabe/mlconvgec2018/software/fairseq-py
++ NBEST_RERANKER=/mnt/data/okabe/mlconvgec2018/software/nbest-reranker
++ beam=12
++ nbest=12
++ threads=12
++ mkdir -p ./data/test/conll14st-test/output
++ /mnt/data/okabe/mlconvgec2018/scripts/apply_bpe.py -c /mnt/data/okabe/mlconvgec2018/models/bpe_model/train.bpe.model
++ CUDA_VISIBLE_DEVICES=0
++ python /mnt/data/okabe/mlconvgec2018/software/fairseq-py/interactive.py --no-progress-bar --path --beam 12 --nbest 12 --interactive --workers 12 /mnt/data/okabe/mlconvgec2018/models/data_bin
usage: interactive.py [-h] [--no-progress-bar] [--log-interval N]
[--log-format {json,none,simple,tqdm}] [--seed N]
[--task TASK] [--skip-invalid-size-inputs-valid-test]
[--max-tokens N] [--max-sentences N]
[--gen-subset SPLIT] [--num-shards N] [--shard-id ID]
[--path FILE] [--remove-bpe [REMOVE_BPE]] [--cpu]
[--quiet] [--beam N] [--nbest N] [--max-len-a N]
[--max-len-b N] [--min-len N] [--no-early-stop]
[--unnormalized] [--no-beamable-mm] [--lenpen LENPEN]
[--unkpen UNKPEN] [--replace-unk [REPLACE_UNK]]
[--score-reference] [--prefix-size PS] [--sampling]
[--sampling-topk PS] [--sampling-temperature N]
[--buffer-size N]
interactive.py: error: argument --path: expected one argument
I found a similar issue someone had(you replied to him as well) so I used interactive.py instead of using generate.py. Sadly, I still have an error.
Thanks for your cooperate!
from mlconvgec2018.
from mlconvgec2018.
Thank you very much!
from mlconvgec2018.
Related Issues (20)
- Using interactive instead of generate to evaluate HOT 1
- Python error: <stdin> is a directory, cannot continue HOT 2
- the size of training dataset? HOT 2
- How to use language model (94Bcclm.trie)? HOT 2
- TypeError: iter() returned non-iterator of type 'NBestList' HOT 9
- An error about Compile and install PyTorch(0.2.0) HOT 5
- Accuracy of trained model? HOT 12
- Fairseq-py Installation Issue HOT 5
- About training data
- reranker error HOT 6
- pytorch version? HOT 3
- pre-trainined embeddings. HOT 1
- 'Levenshtein greater than source size' when training re-ranker HOT 1
- Output directory error while running run.sh in google colab HOT 1
- ImportError: cannot import name 'libbleu' from 'fairseq' HOT 3
- Requesting NUCLE dataset 3.2
- Error loading state_size in FConvModel : size mismatch in encoder-decoder weights
- General question: GEC data preprocessing
- Can this model be used for any language?
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from mlconvgec2018.